© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 7247
    Prev
    Next
    INDEX
    Explanations

    scientific and medical terms or discussions

    oai_token-act-pair · gpt-3.5-turbo

    references to medical research and its findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Franch
    -0.70
    Priv
    -0.69
    Quotes
    -0.67
    iquette
    -0.67
     Darrell
    -0.67
    Jimmy
    -0.65
    Tre
    -0.65
    Privacy
    -0.65
     Drama
    -0.64
    Chair
    -0.62
    POSITIVE LOGITS
     biologically
    1.18
     biological
    1.09
     organisms
    1.03
     chemically
    1.02
     enzymes
    1.00
     proteins
    0.98
     enzyme
    0.97
     pollen
    0.96
     bacterial
    0.96
     microbial
    0.96
    Activations Density 1.796%

    No Known Activations